Lessons learned on using High-Performance Computing and Data Science Methods towards understanding the Acute Respiratory Distress Syndrome (ARDS)

Acute Respiratory Distress Syndrome (ARDS), also known as noncardiogenic pulmonary edema, is a severe condition that affects around one in ten-thousand people every year with life-threatening consequences. Its pathophysiology is characterized by bronchoalveolar injury and alveolar collapse (i.e., atelectasis), whereby its patient diagnosis is based on the so-called 'Berlin Definition'. One common practice in Intensive Care Units (ICUs) is to use lung recruitment manoeuvres (RMs) in ARDS to open up unstable, collapsed alveoli using a temporary increase in transpulmonary pressure. Many RMs have been proposed, but there is also confusion regarding the optimal way to achieve and maintain alveolar recruitment in ARDS. Therefore, the best solution to prevent lung damages by ARDS is to identify the onset of ARDS which is still a matter of research. Determining ARDS disease onset, progression, diagnosis, and treatment required algorithmic support which in turn raises the demand for cutting-edge computing power. This paper thus describes several different data science approaches to better understand ARDS, such as using time series analysis and image recognition with deep learning methods and mechanistic modelling using a lung simulator. In addition, we outline how High-Performance Computing (HPC) helps in both cases. That also includes porting the mechanistic models from serial MatLab approaches and its modular supercomputer designs. Finally, without losing sight of discussing the datasets, their features, and their relevance, we also include broader selected lessons learned in the context of ARDS out of our Smart Medical Information Technology for Healthcare (SMITH) research project. The SMITH consortium brings together technologists and medical doctors of nine hospitals, whereby the ARDS research is performed by our Algorithmic Surveillance of ICU (ASIC) patients team. The paper thus also describes how it is essential that HPC experts team up with medical doctors that usually lack the technical and data science experience and contribute to the fact that a wealth of data exists, but ARDS analysis is still slowly progressing. We complement the ARDS findings with selected insights from our Covid-19 research under the umbrella of the European Open Science Cloud (EOSC) fast track grant, a very similar application field. © 2022 Croatian Society MIPRO.

[Nationwide exposure model for COVID-19 intensive care unit admission]. / Bundesweites Belastungsmodell für Intensivstationen durch COVID-19.

BACKGROUND: Forecasting models for intensive care occupancy of coronavirus disease 2019 (COVID-19) patients are important in the current pandemic for strategic planning of patient allocation and avoidance of regional overcrowding. They are often trained entirely on retrospective infection and occupancy data, which can cause forecast uncertainty to grow exponentially with the forecast horizon. METHODOLOGY: We propose an alternative modeling approach in which the model is created largely independent of the occupancy data being simulated. The distribution of bed occupancies for patient cohorts is calculated directly from occupancy data from "sentinel clinics". By coupling with infection scenarios, the prediction error is constrained by the error of the infection dynamics scenarios. The model allows systematic simulation of arbitrary infection scenarios, calculation of bed occupancy corridors, and sensitivity analyses with respect to protective measures. RESULTS: The model was based on hospital data and by adjusting only two parameters of data in the Aachen city region and Germany as a whole. Using the example of the simulation of the respective bed occupancy rates for Germany as a whole, the loading model for the calculation of occupancy corridors is demonstrated. The occupancy corridors form barriers for bed occupancy in the event that infection rates do not exceed specific thresholds. In addition, lockdown scenarios are simulated based on retrospective events. DISCUSSION: Our model demonstrates that a significant reduction in forecast uncertainty in occupancy forecasts is possible by selectively combining data from different sources. It allows arbitrary combination with infection dynamics models and scenarios, and thus can be used both for load forecasting and for sensitivity analyses for expected novel spreading and lockdown scenarios.